Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'many' preceding a prepositional phrase or noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating commonality or generalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cause
    -0.80
    anyon
    -0.77
    dor
    -0.76
    riber
    -0.76
    aeus
    -0.75
    ħĭ
    -0.71
    OUNT
    -0.71
    kefeller
    -0.70
    NI
    -0.70
    ornia
    -0.70
    POSITIVE LOGITS
     others
    0.91
     other
    0.90
     modern
    0.85
     contemporary
    0.83
     dictators
    0.82
     aspects
    0.81
     professions
    0.81
     things
    0.79
     mammals
    0.78
     clich
    0.78
    Act Density 0.140%

    No Known Activations